MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models

• URL: http://arxiv.org/abs/2604.10971v1
• Date: Mon, 13 Apr 2026 04:14:56 GMT
• Title: MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models
• Abstract summary: We present MMR-AD, which is a benchmark for both training and evaluating MLLM-based AD models.<n>We also propose a baseline model, Anomaly-R1, which is a reasoning-based AD model that learns from the CoT data.<n>Our experiments show that our Anomaly-R1 achieves remarkable improvements over generalist MLLMs in both anomaly detection and localization.
• Score: 16.60737807862461
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the progress of industrial anomaly detection, general anomaly detection (GAD) is an emerging trend and also the ultimate goal. Unlike the conventional single- and multi-class AD, general AD aims to train a general AD model that can directly detect anomalies in diverse novel classes without any retraining or fine-tuning on the target data. Recently, Multimodal Large Language Models (MLLMs) have shown great promise in achieving general anomaly detection due to their revolutionary visual understanding and language reasoning capabilities. However, MLLM's general AD ability remains underexplored due to: (1) MLLMs are pretrained on amounts of data sourced from the Web, these data still have significant gaps with the data in AD scenarios. Moreover, the image-text pairs during pretraining are also not specifically for AD tasks. (2) The current mainstream AD datasets are image-based and not yet suitable for post-training MLLMs. To facilitate MLLM-based general AD research, we present MMR-AD, which is a comprehensive benchmark for both training and evaluating MLLM-based AD models. With MMR-AD, we reveal that the AD performance of current SOTA generalist MLLMs still falls far behind the industrial requirements. Based on MMR-AD, we also propose a baseline model, Anomaly-R1, which is a reasoning-based AD model that learns from the CoT data in MMR-AD and is further enhanced by reinforcement learning. Extensive experiments show that our Anomaly-R1 achieves remarkable improvements over generalist MLLMs in both anomaly detection and localization.

Related papers

• Agentic ML Exploration (A-MLE) for Ads Ranking [15.303958185909982]
  Agentic ML Exploration systematically explores ML techniques across a portfolio of ads ranking models.<n>A-MLE decomposes ML iteration into five stages involving hypothesis generation, exploration strategy, experiment execution, result analysis and shared knowledge substrate.<n>We deploy A-MLE across a representative set of large-scale ads ranking models and evaluate it along a tiered capability framework.
  arXiv  Detail & Related papers  (2026-09-08T04:48:03Z)
• VAN-AD: Visual Masked Autoencoder with Normalizing Flow For Time Series Anomaly Detection [17.972690703544764]
  Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems.<n>In this paper, we investigate the applicability of large-scale vision models to TSAD.<n>We propose VAN-AD, a novel MAE-based framework for TSAD.
  arXiv  Detail & Related papers  (2026-03-27T08:48:59Z)
• AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison [89.0720931534819]
  We present AD-Copilot, an interactive MLLM specialized for industrial anomaly detection (IAD)<n>We first design a novel data pipeline to mine inspection knowledge from sparsely labeled industrial images.<n>We then generate precise samples for captioning, VQA, and defect localization, yielding a large-scale multimodal Comparison-AD rich in semantic signals for IAD.<n>Experiments show that AD-Copilot achieves 82.3% accuracy on the MMAD benchmark, outperforming all other models without any data leakage.
  arXiv  Detail & Related papers  (2026-03-14T06:14:44Z)
• General-Reasoner: Advancing LLM Reasoning Across All Domains [64.70599911897595]
  Reinforcement learning (RL) has recently demonstrated strong potential in enhancing the reasoning capabilities of large language models (LLMs)<n>We propose General-Reasoner, a novel training paradigm designed to enhance LLM reasoning capabilities across diverse domains.<n>We train a series of models and evaluate them on a wide range of datasets covering wide domains like physics, chemistry, finance, electronics etc.
  arXiv  Detail & Related papers  (2025-05-20T17:41:33Z)
• AnomalyR1: A GRPO-based End-to-end MLLM for Industrial Anomaly Detection [40.34270276536052]
  Industrial Anomaly Detection (IAD) poses a formidable challenge due to the scarcity of defective samples.<n>Traditional approaches, often constrained by hand-crafted features or domain-specific expert models, struggle to address this limitation.<n>We introduce AnomalyR1, a pioneering framework that leverages VLM-R1, a Multimodal Large Language Model (MLLM) renowned for its exceptional generalization and interpretability.
  arXiv  Detail & Related papers  (2025-04-16T09:48:41Z)
• AD-LLM: Benchmarking Large Language Models for Anomaly Detection [42.48028199802796]
  This paper introduces AD-LLM, the first benchmark that evaluates how large language models can help with anomaly detection.<n>We examine three key tasks: zero-shot detection, using LLMs' pre-trained knowledge to perform AD without tasks-specific training; data augmentation, generating synthetic data and category descriptions to improve AD models; and model selection, using LLMs to suggest unsupervised AD models.
  arXiv  Detail & Related papers  (2024-12-15T10:22:14Z)
• From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons [85.99268361356832]
  We introduce a process of adapting an MLLM to a Generalist Embodied Agent (GEA)<n>GEA is a single unified model capable of grounding itself across varied domains through a multi-embodiment action tokenizer.<n>Our findings reveal the importance of training with cross-domain data and online RL for building generalist agents.
  arXiv  Detail & Related papers  (2024-12-11T15:06:25Z)
• On Domain-Adaptive Post-Training for Multimodal Large Language Models [78.65220510401045]
  This paper systematically investigates domain adaptation of MLLMs via post-training.<n>We focus on data synthesis, training pipeline, and task evaluation.<n>We conduct experiments in high-impact domains such as biomedicine, food, and remote sensing.
  arXiv  Detail & Related papers  (2024-11-29T18:42:28Z)
• Simplifying Multimodality: Unimodal Approach to Multimodal Challenges in Radiology with General-Domain Large Language Model [3.012719451477384]
  We introduce MID-M, a novel framework that leverages the in-context learning capabilities of a general-domain Large Language Model (LLM) to process multimodal data via image descriptions. MID-M achieves a comparable or superior performance to task-specific fine-tuned LMMs and other general-domain ones, without the extensive domain-specific training or pre-training on multimodal data. The robustness of MID-M against data quality issues demonstrates its practical utility in real-world medical domain applications.
  arXiv  Detail & Related papers  (2024-04-29T13:23:33Z)
• Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark [101.23684938489413]
  Anomaly detection (AD) is often focused on detecting anomalies for industrial quality inspection and medical lesion examination. This work first constructs a large-scale and general-purpose COCO-AD dataset by extending COCO to the AD field. Inspired by the metrics in the segmentation field, we propose several more practical threshold-dependent AD-specific metrics.
  arXiv  Detail & Related papers  (2024-04-16T17:38:26Z)
• Data-Efficient and Interpretable Tabular Anomaly Detection [54.15249463477813]
  We propose a novel framework that adapts a white-box model class, Generalized Additive Models, to detect anomalies. In addition, the proposed framework, DIAD, can incorporate a small amount of labeled data to further boost anomaly detection performances in semi-supervised settings.
  arXiv  Detail & Related papers  (2022-03-03T22:02:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.